Skip to main content
main-content

Tipp

Weitere Kapitel dieses Buchs durch Wischen aufrufen

2019 | OriginalPaper | Buchkapitel

A Recommender System for Complex Real-World Applications with Nonlinear Dependencies and Knowledge Graph Context

verfasst von: Marcel Hildebrandt, Swathi Shyam Sunder, Serghei Mogoreanu, Mitchell Joblin, Akhil Mehta, Ingo Thon, Volker Tresp

Erschienen in: The Semantic Web

Verlag: Springer International Publishing

share
TEILEN

Abstract

Most latent feature methods for recommender systems learn to encode user preferences and item characteristics based on past user-item interactions. While such approaches work well for standalone items (e.g., books, movies), they are not as well suited for dealing with composite systems. For example, in the context of industrial purchasing systems for engineering solutions, items can no longer be considered standalone. Thus, latent representation needs to encode the functionality and technical features of the engineering solutions that result from combining the individual components. To capture these dependencies, expressive and context-aware recommender systems are required. In this paper, we propose NECTR, a novel recommender system based on two components: a tensor factorization model and an autoencoder-like neural network. In the tensor factorization component, context information of the items is structured in a multi-relational knowledge base encoded as a tensor and latent representations of items are extracted via tensor factorization. Simultaneously, an autoencoder-like component captures the non-linear interactions among configured items. We couple both components such that our model can be trained end-to-end. To demonstrate the real-world applicability of NECTR, we conduct extensive experiments on an industrial dataset concerned with automation solutions. Based on the results, we find that NECTR outperforms state-of-the-art methods by approximately 50% with respect to a set of standard performance metrics.
Fußnoten
1
The anonymized data along with implementations of all methods that we consider in this paper can be found under https://​github.​com/​m-hildebrandt/​NECTR.
 
Literatur
1.
Zurück zum Zitat Bell, R.M., Koren, Y., Volinsky, C.: The Bellkor 2008 solution to the Netflix prize. Statistics Research Department at AT&T Research 1 (2008) Bell, R.M., Koren, Y., Volinsky, C.: The Bellkor 2008 solution to the Netflix prize. Statistics Research Department at AT&T Research 1 (2008)
2.
Zurück zum Zitat Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. ArXiv e-prints, June 2012 Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. ArXiv e-prints, June 2012
3.
Zurück zum Zitat Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Advances in Neural Information Processing Systems, pp. 2787–2795 (2013) Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Advances in Neural Information Processing Systems, pp. 2787–2795 (2013)
4.
Zurück zum Zitat Burke, R.: Hybrid recommender systems: survey and experiments. User Model. User-Adapt. Interact. 12(4), 331–370 (2002) CrossRef Burke, R.: Hybrid recommender systems: survey and experiments. User Model. User-Adapt. Interact. 12(4), 331–370 (2002) CrossRef
5.
Zurück zum Zitat Choi, S.M., Han, Y.S.: A content recommendation system based on category correlations. In: 2010 Fifth International Multi-Conference on Computing in the Global Information Technology (ICCGI), pp. 66–70. IEEE (2010) Choi, S.M., Han, Y.S.: A content recommendation system based on category correlations. In: 2010 Fifth International Multi-Conference on Computing in the Global Information Technology (ICCGI), pp. 66–70. IEEE (2010)
6.
Zurück zum Zitat Dong, X., Yu, L., Wu, Z., Sun, Y., Yuan, L., Zhang, F.: A hybrid collaborative filtering model with deep structure for recommender systems. In: AAAI, pp. 1309–1315 (2017) Dong, X., Yu, L., Wu, Z., Sun, Y., Yuan, L., Zhang, F.: A hybrid collaborative filtering model with deep structure for recommender systems. In: AAAI, pp. 1309–1315 (2017)
8.
Zurück zum Zitat Hinton, G., Deng, L., Yu, D., Dahl, G.: Deep neural networks for acoustic modeling in speech recognition. Signal Process. Mag. 29, 82–97 (2012) CrossRef Hinton, G., Deng, L., Yu, D., Dahl, G.: Deep neural networks for acoustic modeling in speech recognition. Signal Process. Mag. 29, 82–97 (2012) CrossRef
9.
Zurück zum Zitat Krizhevsky, A.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012) Krizhevsky, A.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)
10.
Zurück zum Zitat Linden, G., Smith, B., York, J.: Amazon.com recommendations: item-to-item collaborative filtering. IEEE Internet Comput. 7(1), 76–80 (2003) CrossRef Linden, G., Smith, B., York, J.: Amazon.com recommendations: item-to-item collaborative filtering. IEEE Internet Comput. 7(1), 76–80 (2003) CrossRef
12.
Zurück zum Zitat Meng, Q., Catchpoole, D., Skillicorn, D., Kennedy, P.J.: Relational autoencoder for feature extraction. ArXiv e-prints, February 2018 Meng, Q., Catchpoole, D., Skillicorn, D., Kennedy, P.J.: Relational autoencoder for feature extraction. ArXiv e-prints, February 2018
13.
Zurück zum Zitat Nickel, M., Tresp, V., Kriegel, H.P.: A three-way model for collective learning on multi-relational data. In: ICML, vol. 11, pp. 809–816 (2011) Nickel, M., Tresp, V., Kriegel, H.P.: A three-way model for collective learning on multi-relational data. In: ICML, vol. 11, pp. 809–816 (2011)
14.
Zurück zum Zitat Rifai, S., Vincent, P., Muller, X., Glorot, X., Bengio, Y.: Contracting auto-encoders: explicit invariance during feature extraction. In: Proceedings of the Twenty-Eight International Conference on Machine Learning (ICML 2011) (2011) Rifai, S., Vincent, P., Muller, X., Glorot, X., Bengio, Y.: Contracting auto-encoders: explicit invariance during feature extraction. In: Proceedings of the Twenty-Eight International Conference on Machine Learning (ICML 2011) (2011)
15.
Zurück zum Zitat Strub, F., Gaudel, R., Mary, J.: Hybrid recommender system based on autoencoders. In: Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, pp. 11–16. ACM (2016) Strub, F., Gaudel, R., Mary, J.: Hybrid recommender system based on autoencoders. In: Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, pp. 11–16. ACM (2016)
16.
Zurück zum Zitat Weston, J., Chopra, S., Adams, K.: TagSpace: semantic embeddings from hashtags. In: Empirical Methods in Natural Language Processing (2014) Weston, J., Chopra, S., Adams, K.: TagSpace: semantic embeddings from hashtags. In: Empirical Methods in Natural Language Processing (2014)
Metadaten
Titel
A Recommender System for Complex Real-World Applications with Nonlinear Dependencies and Knowledge Graph Context
verfasst von
Marcel Hildebrandt
Swathi Shyam Sunder
Serghei Mogoreanu
Mitchell Joblin
Akhil Mehta
Ingo Thon
Volker Tresp
Copyright-Jahr
2019
DOI
https://doi.org/10.1007/978-3-030-21348-0_12